ChineseTaiwaneseWhisper and Taiwanese-Whisper

These are competitors offering alternative implementations for the same task—fine-tuning OpenAI's Whisper model for Taiwanese speech recognition—with the first providing broader Chinese/Taiwanese language support while the second focuses exclusively on Taiwanese.

Taiwanese-Whisper
32
Emerging
Maintenance 0/25
Adoption 9/25
Maturity 8/25
Community 17/25
Maintenance 0/25
Adoption 7/25
Maturity 8/25
Community 17/25
Stars: 70
Forks: 12
Downloads:
Commits (30d): 0
Language: Python
License:
Stars: 37
Forks: 8
Downloads:
Commits (30d): 0
Language: Python
License:
No License Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About ChineseTaiwaneseWhisper

sandy1990418/ChineseTaiwaneseWhisper

This repository focuses on leveraging OpenAI's Whisper model for speech recognition in Chinese (Mandarin) and Taiwanese Hokkien languages. It includes tools and scripts for data preprocessing, model training, and evaluation, tailored to improve speech recognition accuracy for these languages.

This project helps professionals accurately transcribe spoken Chinese (Mandarin) and Taiwanese Hokkien audio into text. It takes audio recordings or live streams as input and produces precise text transcripts, which can include timestamps. This is ideal for researchers, content creators, or businesses needing reliable speech-to-text for these specific languages.

audio-transcription language-services market-research media-analysis content-localization

About Taiwanese-Whisper

ga642381/Taiwanese-Whisper

fine-tune Whipser model for Taiwanese speech recognition

This project helps developers enhance the accuracy of speech-to-text conversion for spoken Taiwanese Hokkien. It takes existing Taiwanese speech recordings and their corresponding text transcripts to refine an AI model, ultimately producing a more precise speech recognition model tailored for Taiwanese. Developers working with speech technology for Taiwanese language applications would use this.

speech-recognition Taiwanese-Hokkien natural-language-processing AI-model-training

Scores updated daily from GitHub, PyPI, and npm data. How scores work